Whitford, Daniel

Background Improving safety in healthcare has been paramount for decades, yet despite major attention and investment, improvement has remained incremental. Patient safety is a major concern in US healthcare, leading to significant harm and economic losses annually. Accurately identifying safety events remains difficult due to methodological discrepancies and lack of standardisation. This study evaluated the feasibility of implementing a standardised case-review methodology and safety-event taxonomy across diverse hospital settings to assess opportunities for improvement (OFIs) and compare findings with traditional definitions. Methods This multicentre retrospective cohort study reports data from 103 hospitals across the USA and Canada between 2016 and 2023. A multivariable logistic regression was performed to test case reviews for differences in the presence of one or more OFIs across several hospital types (bed size, academic status, urban setting, trauma level and Centres for Medicare and Medicaid Services overall star rating) and patient characteristics (age, gender, length of stay, admission and discharge code status and mortality). Results 19 181 cases were reviewed across the Learning Health System Collaborative, with a median of 107 reviews per hospital. Mortality was the most common cohort selection, studied by 91 hospitals (88%). At least one OFI was identified in 12 714 cases (66.3%). The logistic regression analysis found that all hospital characteristics and patient age, length of stay, code status and discharge disposition were significantly associated with at least one OFI. Of the 46 444 OFIs identified, 41 439 (89%) were from categories focused on omissions of care. The categories of end-of-life, documentation and treatment/care alone accounted for 25 980 OFIs (56%). Conclusion The highest volumes of safety-related OFIs were associated with omissions of care, as opposed to the traditional definition of patient safety, which primarily includes outcomes from acts of commission.

Abstract Objective We aimed to develop a model for accurate prediction of general care inpatient deterioration. Materials and Methods Training and internal validation datasets were built using 2-year data from a quaternary hospital in the Midwest. Model training used gradient boosting and feature engineering (clinically relevant interactions, time-series information) to predict general care inpatient deterioration (resuscitation call, intensive care unit transfer, or rapid response team call) in 24 hours. Data from a tertiary care hospital in the Southwest were used for external validation. C-statistic, sensitivity, positive predictive value, and alert rate were calculated for different cutoffs and compared with the National Early Warning Score. Sensitivity analysis evaluated prediction of intensive care unit transfer or resuscitation call. Results Training, internal validation, and external validation datasets included 24 500, 25 784 and 53 956 hospitalizations, respectively. The Mayo Clinic Early Warning Score (MC-EWS) demonstrated excellent discrimination in both the internal and external validation datasets (C-statistic = 0.913, 0.937, respectively), and results were consistent in the sensitivity analysis (C-statistic = 0.932 in external validation). At a sensitivity of 73%, MC-EWS would generate 0.7 alerts per day per 10 patients, 45% less than the National Early Warning Score. Discussion Low alert rates are important for implementation of an alert system. Other early warning scores developed for the general care ward have achieved lower discrimination overall compared with MC-EWS, likely because MC-EWS includes both nursing assessments and extensive feature engineering. Conclusions MC-EWS achieved superior prediction of general care inpatient deterioration using sophisticated feature engineering and a machine learning approach, reducing alert rate.

Objective Create a score to identify patients at risk of death or hospice placement who may benefit from goals of care discussion earlier in the hospitalisation. Design Retrospective cohort study to develop a risk index using multivariable logistic regression. Setting Two tertiary care hospitals in Southeastern Minnesota. Participants 92 879 adult general care admissions (50% male, average age 60 years). Primary and secondary outcome measures Our outcome measure was an aggregate of inhospital death or discharge to hospice. Predictor variables for the model encompassed comorbidities, nutrition status, functional status, demographics, fall risk, mental status, Charlson Comorbidity Index and acuity of illness on admission. Resuscitation status, race, geographic area of residence and marital status were added as covariates to account for confounding. Results Inhospital mortality and discharge to hospice were rare, with incidences of 1.2% and 0.8%, respectively. The Hospital End-of-Life Prognostic Score (HELPS) demonstrated good discrimination (C-statistic=0.866 in derivation set and 0.834 in validation set). The patients with the highest 5% of scores had an 8% risk of the outcome measure, relative risk 12.9 (10.9–15.4) when compared to the bottom 95%. Conclusions HELPS is able to identify patients with a high risk of inhospital death or need for hospice at discharge. These patients may benefit from early goals of care discussions.